theserverless.dev InferenceList

Compare

Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.

Monthly bill

Token models use the token counts. Other models use units times the flat rate.

Google: Gemma 4 26B A4B$0.43
Qwen: Qwen3 Next 80B A3B Instruct$1.39

Lowest bill: Google: Gemma 4 26B A4B · $0.43

Add another

Search by name, then add up to four.

Google: Gemma 4 26B A4BQwen: Qwen3 Next 80B A3B Instruct
ProviderIo NetIo Net
Modalitytext, imagetext
Context262K262K
Input$0.106/1M$0.1083/1M
Output$0.328/1M$1.283/1M
Cache read$0.053/1M$0.0542/1M